© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60608
    Prev
    Next
    INDEX
    Explanations

    make sense / doesn't make sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ì°©
    -0.09
    æľīåħ³äºĭ项
    -0.09
    ä¸įå¾Ĺä»İäºĭ
    -0.09
    ATAN
    -0.08
    å®ŀè·µè¯ģæĺİ
    -0.08
    æķ¬è¯·åħ³æ³¨
    -0.08
    è¿Ħ
    -0.08
    æľĢæĸ°æ¶Īæģ¯
    -0.08
    æŃ¤èµ·
    -0.08
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.08
    POSITIVE LOGITS
    é¢ĺæĦı
    0.09
    æŀģäºĨ
    0.08
     logically
    0.07
    åĽ½
    0.07
     why
    0.06
    è±ģçĦ¶
    0.06
    æĥħçIJĨ
    0.06
    éģĵçIJĨ
    0.06
    omen
    0.06
    为ä¸Ģ个
    0.06
    Activations Density 0.014%

    No Known Activations